Analyzing Promotion Effectiveness in Fashion Retailing Using Quantile Regression

Abstract

Since the industry standard approach to judge on the effectiveness of promotion is based on the impact on expected sales it cannot grasp other impacts in the distribution of future sales. Since retailers operate with very high strategic service level targets (e.g. 98%) high quantiles of the sales distribution matter more than expected sales, which calls for quantile regression. There are more merits from this approach than forecasting high quantiles: Using real-world data from a fashion retail store i show that the impact of promotion can turn from insignificant to significantly harmful. Choosing quantile regression requires special diagnostics. The quality of forecasting high quantiles should be measured by the implied stock outs. Ideally, the stock outs would form a Bernoulli trials process with probability 100% minus service level target (e.g. 2%). This can be tested with backtests from the risk management literature as is shown in a real-world case.

Keywords: Forecasting, Inventory, Retailing, Backtesting, Fashion

JEL Classification: M1, M2, M3, C1